# US 2024/0203413 A1 · Selecting an automated assistant as the primary automated assistant for a device based on determined affinity scores for candidate automated assistants

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0203413 A1
- Document ID: US20240203413A1
- Status: Published application
- Kind: A1
- Application number: 18/083,429
- Filed: 2022-12-16
- Published: 2024-06-20
- Earliest claimed: 2022-12-16
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Matthew Sharifi; Victor Carbune
- Web page: https://patentgrep.com/patent/US20240203413A1

## CPC

- G06F 9/5044: {considering hardware capabilities}
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G06F 9/5055: {considering software capabilities, i.e. software resources associated or available to the machine}
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G06F 2209/501: Performance criteria
- G06F 2209/502: Proximity
- G06F 2209/5021: Priority
- G06F 2209/503: Resource availability
- G06F 2209/506: Constraint
- G10L 2015/223: {Execution procedure of a spoken command}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Implementations related to selecting a primary automated assistant for a given automated assistant device that is connected to one or more other automated assistant devices in an ecosystem of connected devices. An affinity score is generated for each of a plurality of candidate automated assistants that are capable of executing on the automated assistant device. The affinity score of a given automated assistant for an automated assistant device is indicative of suitability of the automated assistant for the automated assistant device. One of the candidate automated assistants is selected as the primary automated assistant for the device. The primary automated assistant is prioritized when resources of the automated assistant device are allocated to automated assistants executing on the automated assistant device.

## Claims

### Claim 1

A computer implemented method, comprising:
identifying an automated assistant device, wherein the automated assistant device is configured to execute a plurality of automated assistants, and wherein the automated assistant device is part of an ecosystem of connected devices;
for each of the plurality of automated assistants, determining a corresponding affinity measure, wherein the corresponding affinity measure for a given automated assistant is indicative of suitability of the given automated assistant to fulfill requests of the user, and wherein the corresponding affinity measure for the given automated assistant is based on capabilities of the automated assistant device to execute the corresponding automated assistant;
selecting, based on the affinity measures, a primary automated assistant from the plurality of automated assistants; and
prioritizing the primary automated assistant when allocating resources of the automated assistant device and in lieu of other automated assistants of the plurality of automated assistants executing on the automated assistant device.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining each of the corresponding affinity measures is based, at least in part, on a descriptor of the automated assistant device.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining each of the corresponding affinity measures is based, at least in part, on a location of the automated assistant device.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining each of the corresponding affinity measures is based, at least in part, on location of one or more other connected devices.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining each of the corresponding affinity measures is based, at least in part, on resource requirements of the given automated assistant.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining each of the corresponding affinity measures is based, at least in part, on previous requests of the user that were processed by one or more of the automated assistants executing on the automated assistant device.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining the affinity measure of a given automated assistant is based, at least in part, on a number of requests previously processed by the given automated assistant.

### Claim 8 (depends on 1)

The method of claim 1, wherein selecting the primary automated assistant includes:
selecting, as the primary automated assistant, the automated assistant with the corresponding affinity score that is highest amongst all of the corresponding affinity scores.

### Claim 9 (depends on 1)

The method of claim 1, wherein selecting the primary automated assistant includes:
determining that the automated assistant with the highest affinity score is a primary automated assistant of one of the connected devices; and
selecting, as the primary automated assistant, the automated assistant with the next highest affinity score as the primary assistant of the automated assistant device.

### Claim 10 (depends on 1)

The method of claim 1, wherein prioritizing the primary automated assistant includes:
determining that the primary automated assistant and a second automated assistant executing on the automated assistant device require a portion of memory space of the automated assistant device; and
authorizing the primary automated assistant to utilize the portion of memory space in lieu of authorizing the second automated assistant to utilize the portion of memory space.

### Claim 11 (depends on 1)

The method of claim 1, wherein prioritizing the primary automated assistant includes:
determining that the primary automated assistant and a second automated assistant executing on the automated assistant device require usage of a hardware component of the automated assistant device; and
authorizing the primary automated assistant to utilize the hardware component in lieu of authorizing the second automated assistant to utilize the hardware component.

### Claim 12 (depends on 11)

The method of claim 11, wherein the hardware component is a digital signal processor.

### Claim 13

A system, comprising:
a processor, a computer-readable memory, one or more computer-readable storage media, and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable to:
identify an automated assistant device, wherein the automated assistant device is configured to execute a plurality of automated assistants, and wherein the automated assistant device is part of an ecosystem of connected devices;
for each of the plurality of automated assistants, determine a corresponding affinity measure, wherein the corresponding affinity measure for a given automated assistant is indicative of suitability of the given automated assistant to fulfill requests of the user, and wherein the corresponding affinity measure for the given automated assistant is based on capabilities of the automated assistant device to execute the corresponding automated assistant;
select, based on the affinity measures, a primary automated assistant from the plurality of automated assistants; and
prioritize the primary automated assistant when allocating resources of the automated assistant device and in lieu of other automated assistants of the plurality of automated assistants executing on the automated assistant device.

### Claim 14 (depends on 13)

The system of claim 13, wherein determining each of the corresponding affinity measures is based, at least in part, on a descriptor of the automated assistant device.

### Claim 15 (depends on 13)

The system of claim 13, wherein determining each of the corresponding affinity measures is based, at least in part, on a location of the automated assistant device.

### Claim 16 (depends on 13)

The system of claim 13, wherein determining each of the corresponding affinity measures is based, at least in part, on location of one or more other connected devices.

### Claim 17 (depends on 13)

The system of claim 13, wherein determining each of the corresponding affinity measures is based, at least in part, on resource requirements of the given automated assistant.

### Claim 18 (depends on 13)

The system of claim 13, wherein determining each of the corresponding affinity measures is based, at least in part, on previous requests of the user that were processed by one or more of the automated assistants executing on the automated assistant device.

### Claim 19 (depends on 13)

The system of claim 13, wherein determining the affinity measure of a given automated assistant is based, at least in part, on a number of requests previously processed by the given automated assistant.

### Claim 20 (depends on 13)

The system of claim 13, wherein selecting the primary automated assistant includes:
selecting, as the primary automated assistant, the automated assistant with the corresponding affinity score that is highest amongst all of the corresponding affinity scores.
